This paper describes the reliability of a dialogue structure coding scheme which is based on utterance function, game structure, and higher level transaction structure, and which has been applied to a corpus of spontaneous task-oriented spoken dialogues. 1.

We have implemented an application-independent collaboration manager, called Collagen, based on the SharedPlan theory of discourse, and used it to build a software interface agent for a simple air travel application. The software agent provides intelligent, mixed initiative assistance without requiring natural language understanding. A key benefit of the collaboration manager is the automatic construction of an interaction history which is hierarchically structured according to the user's and agent's goals and intentions. To appear in User Modeling and User-Adapted Interaction, Special Issue on Computational Models for Mixed Initiative Interaction. This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Ele...

The Trains project is an effort to build a conversationally proficient planning assistant. A key part of the project is the construction of the Trains system, which provides the research platform for a wide range of issues in natural language understanding, mixedinitiative planning systems, and representing and reasoning about time, actions and events. Four years have now passed since the beginning of the project. Each year we have produced a demonstration system that focused on a dialog that illustrates particular aspects of our research. The commitment to building complete integrated systems is a significant overhead on the research, but we feel it is essential to guarantee that the results constitute real progress in the field. This paper describes the goals of the project, and our experience with the effort so far. This paper is to appear in the Journal of Experimental and Theoretical AI, 1995. The TRAINS project has been funded in part by ONR/ARPA grant N00014-92-J-1512, U.S. Air ...

User-interruption in human-computer interaction (HCI) is an increasingly important problem. Many of the useful advances in intelligent and multitasking computer systems have the significant side effect of greatly increasing user-interruption. This previously innocuous HCI problem has become critical to the successful function of many kinds of modern computer systems. Unfortunately, no HCI design guidelines exist for solving this problem. In fact, theoretical tools do not yet exist for investigating the HCI problem of user-interruption in a comprehensive and generalizable way. This report asserts that a single unifying definition of user-interruption and the accompanying practical taxonomy would be useful theoretical tools for driving effective investigation of this crucial HCI problem. These theoretical tools are constructed here. A comprehensive analysis is conducted through the existing literature. Theoretical constructs from several relevant but diverse fields are identified and discussed. A unifying definition of user-interruption is synthesized. This new definition is supported with an array of postulates, assertions, and a taxonomy of human interruption to facilitate its practical application.

Human one-to-one tutoring has been shown to be a very effective form of instruction. Three contrasting hypotheses, a tutor-centered one, a student-centered one, and an interactive one could all potentially explain the effectiveness of tutoring. To test these hypotheses, analyses focused not only on the effectiveness of the tutors ’ moves, but also on the effectiveness of the students ’ construction on learning, as well as their interaction. The interaction hypothesis is further tested in the second study by manipulating the kind of tutoring tactics tutors were permitted to use. In order to promote a more interactive style of dialogue, rather than a didactic style, tutors were suppressed from giving explanations and feedback. Instead, tutors were encouraged to prompt the students. Surprisingly, students learned just as effectively even when tutors were suppressed from giving explanations and feedback. Their learning in the interactive style of tutoring is attributed to construction from deeper and a greater amount of scaffolding episodes, as well as their greater effort to take control of their own learning by reading more. What they learned from reading was limited, however, by their reading abilities.

This paper is an exploration in the semantics and pragmatics of linguistic feedback, i.e., linguistic mechanisms which enable the participants in spoken interaction to exchange information about basic communicative functions, such as contact, perception, understanding, and attitudinal reactions to the communicated content. Special attention is given to the type of reaction conveyed by feedback utterances, the communicative status of the information conveyed (i. e., the level of awareness and intentionality of the communicating sender), and the context sensitivity of feedback expressions. With regard to context sensitivity, which is one of the most characteristic features of feedback expressions, the discussion focuses on the way in which the type of speech act (mood), the factual polarity and the information status of the preceding utterance influence the interpretation of feedback utterances. The different content dimensions are exemplified by data from recorded dialogues and by data given through linguistic intuition. Finally, two different ways of formalizing the analysis are examined, one using attribute-value matrices and one based on the theory of situation semantics.

When people in conversation refer repeatedly to the same object, they come to use the same terms. This phenomenon, called lexical entrainment, has several possible explanations. Ahistorical accounts appeal only to the informativeness and availability of terms and to the current salience of the object's features. Historical accounts appeal in addition to the recency and frequency of past references and to partner-specific conceptualizations of the object that people achieve interactively. Evidence from 3 experiments favors a historical account and suggests that when speakers refer to an object, they are proposing a conceptualization of it, a proposal their addressees may or may not agree to. Once they do establish a shared conceptualization, a conceptual pact, they appeal to it in later references even when they could use simpler references. Over time, speakers simplify conceptual pacts and, when necessary, abandon them for new conceptualizations. When speakers refer to an object, as with the loafer, one of their goals is to get their addressees to identify the object. Current theories of reference differ on how they manage that. By some theories, speakers design each referring expression with enough information, but no more than enough, to

This paper re-assesses the role of real-time video as a technology to support interpersonal communications at distance. We review three distinct hypotheses about the role of video in the co-ordination of conversational content and process. For each hypothesis, we identify design implications and outstanding research questions derived from current findings. We first evaluate the non-verbal communication hypothesis, namely the prevailing assumption that the role of video is to supplement speech, and embodied in applications such as videoconferencing and videophone. We conclude that previous work has overestimated the importance of video at the expense of audio. This finding has strong implications for the implementation of such systems, and we make recommendations about both synchronisation and bandwidth allocation. Furthermore our own recent studies of workplace interactions point to other communicative functions of video. Current systems have neglected another potentially vital role of...

Abstract not found

We investigate the verbal and nonverbal means for grounding, and propose a design for embodied conversational agents that relies on both kinds of signals to establish common ground in human-computer interaction. We analyzed eye gaze, head nods and attentional focus in the context of a direction-giving task. The distribution of nonverbal behaviors differed depending on the type of dialogue move being grounded, and the overall pattern reflected a monitoring of lack of negative feedback. Based on these results, we present an ECA that uses verbal and nonverbal grounding acts to update dialogue state.